no code implementations • 8 May 2024 • Shuo Shao, Yiming Li, Hongwei Yao, Yiling He, Zhan Qin, Kui Ren
Motivated by this understanding, we design a new watermarking paradigm, $i. e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions.
no code implementations • 7 May 2024 • Yiling He, Junchi Lei, Zhan Qin, Kui Ren
To ensure a comprehensive response to concept drift, it facilitates a coordinated update process for both the classifier and the detector.
no code implementations • 27 Nov 2023 • Mengda Xie, Yiling He, Meie Fang
The former custom-designed human-interpretability retouching framework for adversarial attack by linearizing images while modelling the local processing and retouching decision-making in human retouching behaviour, provides an explicit and reasonable pipeline for understanding the robustness of DNNs against retouching.
1 code implementation • 27 Oct 2023 • Xinyu She, Yue Liu, Yanjie Zhao, Yiling He, Li Li, Chakkrit Tantithamthavorn, Zhan Qin, Haoyu Wang
After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems.
1 code implementation • 10 Aug 2023 • Yiling He, Jian Lou, Zhan Qin, Kui Ren
Although feature attribution (FA) methods can be used to explain deep learning, the underlying classifier is still blind to what behavior is suspicious, and the generated explanation cannot adapt to downstream tasks, incurring poor explanation fidelity and intelligibility.